摘要
对于手势识别来说,骨架数据是一种紧凑且对环境条件稳健的数据模态.最近基于骨架的手势识别研究多使用深度神经网络去提取空间和时间的信息,然而这些方法可能存在复杂的计算和大量的模型参数的问题.为了解决这个问题,我们提出一种轻量高效的手势识别模型.该模型使用从骨架序列上计算出的两种空间几何特征,以及自动学习的运动轨迹特征,然后只使用卷积网络作为骨干网络实现手势分类.最终我们的模型参数量最少情况下仅为0.16 M,计算复杂度最大情况为0.03 GFLOPs.我们在公开的两个数据集上评估了我们的方法,与其他输入为骨架模态的方法相比,我们的方法取得了相应数据集上最好的结果.
Skeleton data is compact and robust to environmental conditions for hand gesture recognition.Recent studies of skeleton-based hand gesture recognition often use deep neural networks to extract spatial and temporal information.However,these methods are likely to have problems such as complicated computation and a large number of model parameters.To solve this problem,this study presents a lightweight and efficient hand gesture recognition model.It uses two spatial geometric features calculated from skeleton sequences and automatically learned motion trajectory features to achieve hand gesture classification with convolutional networks alone as its backbone network.The proposed model has a minimum number of parameters as small as 0.16M and a maximum computational complexity of 0.03 GFLOPs.This method is also evaluated on two public datasets,where it outperforms the other methods that use skeleton modality as input.
作者
赵阳
刘汉超
董兰芳
ZHAO Yang;LIU Han-Chao;DONG Lan-Fang(School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China)
出处
《计算机系统应用》
2022年第11期261-267,共7页
Computer Systems & Applications
基金
国家重点研发计划重点专项(2020YFB1313602)
关键词
动态手势识别
卷积神经网络
动作识别
骨架数据
特征提取
深度学习
dynamic hand gesture recognition
convolutional neural network(CNN)
action recognition
skeleton data
feature extraction
deep learning
